DOCSLIB.ORG

Mathematical Methods in Medical Image Processing

Total Page：16

File Type：pdf, Size：1020Kb

Download full-text PDF Read full-text
Mathematical Methods in Medical Image Processing BULLETIN (New Series) OF THE AMERICAN MATHEMATICAL SOCIETY Volume 00, Number 0, Pages 000–000 S 0273-0979(XX)0000-0 MATHEMATICAL METHODS IN MEDICAL IMAGE PROCESSING SIGURD ANGENENT, ERIC PICHON, AND ALLEN TANNENBAUM Abstract. In this paper, we describe some central mathematical problems in medical imaging. The subject has been undergoing rapid changes driven by better hardware and software. Much of the software is based on novel methods utilizing geometric partial differential equations in conjunction with standard signal/image processing techniques as well as computer graphics fa- cilitating man/machine interactions. As part of this enterprise, researchers have been trying to base biomedical engineering principles on rigorous mathe- matical foundations for the development of software methods to be integrated into complete therapy delivery systems. These systems support the more ef- fective delivery of many image-guided procedures such as radiation therapy, biopsy, and minimally invasive surgery. We will show how mathematics may impact some of the main problems in this area including image enhancement, registration, and segmentation. Contents 1. Introduction 2 2. Outline 3 3. Medical Imaging 3 3.1. Generalities 3 3.2. Imaging Modalities 4 4. Mathematics and Imaging 6 4.1. Artificial Vision 7 4.2. Algorithms and PDEs 7 5. Imaging Problems 9 5.1. Image Smoothing 9 5.2. Image Registration 15 5.3. Image Segmentation 19 6. Conclusion 26 References 27 Key words and phrases. medical imaging, artificial vision, smoothing, registration, segmentation. This research was supported by grants from the NSF, NIH (NAC P41 RR-13218 through Brigham and Women’s Hospital), and the Technion, Israel Insitute of Technology. This work was done under the auspices of the National Alliance for Medical Image Computing (NAMIC), funded by the National Institutes of Health through the NIH Roadmap for Medical Research, Grant U54 EB005149. The authors would like to thank Steven Haker, Ron Kikinis, Guillermo Sapiro, Anthony Yezzi, and Lei Zhu for many helpful conversations on medical imaging and to Bob McElroy for proof- reading the final document. c 0000 (copyright holder) 1 2 SIGURD ANGENENT, ERIC PICHON, AND ALLEN TANNENBAUM 1. Introduction Medical imaging has been undergoing a revolution in the past decade with the advent of faster, more accurate, and less invasive devices. This has driven the need for corresponding software development which in turn has provided a major impetus for new algorithms in signal and image processing. Many of these algorithms are based on partial differential equations and curvature driven flows which will be the main topics of this survey paper. Mathematical models are the foundation of biomedical computing. Basing those models on data extracted from images continues to be a fundamental technique for achieving scientific progress in experimental, clinical, biomedical, and behavioral research. Today, medical images are acquired by a range of techniques across all biological scales, which go far beyond the visible light photographs and microscope images of the early 20th century. Modern medical images may be considered to be geometrically arranged arrays of data samples which quantify such diverse physi- cal phenomena as the time variation of hemoglobin deoxygenation during neuronal metabolism, or the diffusion of water molecules through and within tissue. The broadening scope of imaging as a way to organize our observations of the biophys- ical world has led to a dramatic increase in our ability to apply new processing techniques and to combine multiple channels of data into sophisticated and com- plex mathematical models of physiological function and dysfunction. A key research area is the formulation of biomedical engineering principles based on rigorous mathematical foundations in order to develop general-purpose software methods that can be integrated into complete therapy delivery systems. Such systems support the more effective delivery of many image-guided procedures such as biopsy, minimally invasive surgery, and radiation therapy. In order to understand the extensive role of imaging in the therapeutic process, and to appreciate the current usage of images before, during, and after treatment, we focus our analysis on four main components of image-guided therapy (IGT) and image-guided surgery (IGS): localization, targeting, monitoring, and control. Specifically, in medical imaging we have four key problems: (1) Segmentation - automated methods that create patient-specific models of relevant anatomy from images; (2) Registration - automated methods that align multiple data sets with each other; (3) Visualization - the technological environment in which image-guided pro- cedures can be displayed; (4) Simulation - softwares that can be used to rehearse and plan procedures, evaluate access strategies, and simulate planned treatments. In this paper, we will only consider the first two problem areas. However, it is essential to note that in modern medical imaging, we need to integrate these technologies into complete and coherent image guided therapy delivery systems and validate these integrated systems using performance measures established in particular application areas. We should note that in this survey we touch only upon those aspects of the mathematics of medical imaging reflecting the personal tastes (and prejudices) of the authors. Indeed, we do not discuss a number of very important techniques such MATHEMATICAL METHODS IN MEDICAL IMAGE PROCESSING 3 as wavelets, which have had a significant impact on imaging and signal process- ing; see [60] and the references therein. Several articles and books are available which describe various mathematical aspects of imaging processing such as [67] (segmentation), [83] (curve evolution), and [71, 87] (level set methods). Finally, it is extremely important to note that all the mathematical algorithms which we sketch lead to interactive procedures. This means that in each case there is a human user in the loop (typically a clinical radiologist) who is the ultimate judge of the utility of the procedure, and who tunes the parameters either on or off-line. Nevertheless, there is a major need for further mathematical techniques which lead to more automatic and easier to use medical procedures. We hope that this paper may facilitate a dialogue between the mathematical and medical imaging communities. 2. Outline We briefly outline the subsequent sections of this paper. Section 3 reviews some of the key imaging modalities. Each one has certain advantages and disadvantages, and algorithms tuned to one device may not work as well on another device. Understanding the basic physics of the given modality is often very useful in forging the best algorithm. In Section 4, we describe some of the relevant issues in computer vision and image processing for the medical field as well as sketch some of the partial differential equation (PDE) methods that researchers have proposed to deal with these issues. Section 5 is the heart of this survey paper. Here we describe some of the main mathematical and engineering problems connected with image processing in general and medical imaging in particular. These include image smoothing, registration, and segmentation (see Sections 5.1, 5.2, and 5.3). We show how geometric partial differential equations and variational methods may be used to address some of these problems as well as illustrate some of the various methodologies. Finally in Section 6, we summarize the survey as well as point out some possible future research directions. 3. Medical Imaging 3.1. Generalities. In 1895, Roentgen discovered X-rays and pioneered medical imaging. His initial publication [82] contained a radiograph (i.e. an X-ray generated photograph) of Mrs. Roentgen’s hand; see Figure 3.1(b). For the first time, it was possible to visualize non-invasively (i.e., not through surgery) the interior of the human body. The discovery was widely publicized in the popular press and an “X- ray mania” immediately seized Europe and the United States [30, 47]. Within only a few months, public demonstrations were organized, commercial ventures created and innumerable medical applications investigated; see Figure 3.1(a). The field of radiography was born with a bang1! Today, medical imaging is a routine and essential part of medicine. Pathologies can be observed directly rather than inferred from symptoms. For example, a physician can non-invasively monitor the healing of damaged tissue or the growth of a brain tumor, and determine an appropriate medical response. Medical imaging techniques can also be used when planning or even while performing surgery. For 1It was not understood at that time that X-rays are ionizing radiations and that high doses are dangerous. Many enthusiastic experimenters died of radio-induced cancers. 4 SIGURD ANGENENT, ERIC PICHON, AND ALLEN TANNENBAUM (a) A “bone studio” commer- (b) First radiograph of cial. Mrs. Roentgen’s hand. Figure 3.1. X-ray radiography at the end of the 19th century. example, a neurosurgeon can determine the “best” path in which to insert a needle, and then verify in real time its position as it is being inserted. 3.2. Imaging Modalities. Imaging technology has improved considerably since the end of the 19th century. Many different imaging techniques have been developed and are in clinical use. Because they are based on different physical principles [41], these techniques can be more or less suited to a particular organ or pathology. In practice they are complementary
Load more

Recommended publications
  • An Analytical Introduction to Descriptive Geometry
    An analytical introduction to Descriptive Geometry Adrian B. Biran, Technion { Faculty of Mechanical Engineering Ruben Lopez-Pulido, CEHINAV, Polytechnic University of Madrid, Model Basin, and Spanish Association of Naval Architects Avraham Banai Technion { Faculty of Mathematics Prepared for Elsevier (Butterworth-Heinemann), Oxford, UK Samples - August 2005 Contents Preface x 1 Geometric constructions 1 1.1 Introduction . 2 1.2 Drawing instruments . 2 1.3 A few geometric constructions . 2 1.3.1 Drawing parallels . 2 1.3.2 Dividing a segment into two . 2 1.3.3 Bisecting an angle . 2 1.3.4 Raising a perpendicular on a given segment . 2 1.3.5 Drawing a triangle given its three sides . 2 1.4 The intersection of two lines . 2 1.4.1 Introduction . 2 1.4.2 Examples from practice . 2 1.4.3 Situations to avoid . 2 1.5 Manual drawing and computer-aided drawing . 2 i ii CONTENTS 1.6 Exercises . 2 Notations 1 2 Introduction 3 2.1 How we see an object . 3 2.2 Central projection . 4 2.2.1 De¯nition . 4 2.2.2 Properties . 5 2.2.3 Vanishing points . 17 2.2.4 Conclusions . 20 2.3 Parallel projection . 23 2.3.1 De¯nition . 23 2.3.2 A few properties . 24 2.3.3 The concept of scale . 25 2.4 Orthographic projection . 27 2.4.1 De¯nition . 27 2.4.2 The projection of a right angle . 28 2.5 The two-sheet method of Monge . 36 2.6 Summary . 39 2.7 Examples . 43 2.8 Exercises .
    [Show full text]
  • Computational Anatomy: Model Construction and Application for Anatomical Structures Recognition in Torso CT Images
    The First International Symposium on the Project “Computational Anatomy” Computational Anatomy: Model Construction and Application for Anatomical Structures Recognition in Torso CT Images Hiroshi Fujita #1, Takeshi Hara #2, Xiangrong Zhou #3, Huayue Chen *4, and Hiroaki Hoshi **5 # Department of Intelligent Image Information, Graduate School of Medicine, Gifu University * Department of Anatomy, Graduate School of Medicine, Gifu University ** Department of Radiology, Graduate School of Medicine, Gifu University Yanagido 1-1, Gifu 501-1194, Japan 1 [email protected] 2 [email protected] 3 [email protected] 4 [email protected] 5 [email protected] Abstract—This paper describes the purpose and recent summary advanced CAD system that aims at multi-disease detection of our research work which is a part of research project from multi-organ [2]. The traditional approach for lesion “Computational anatomy for computer-aided diagnosis and detection prepares a pattern for a specific lesion type and therapy: Frontiers of medical image sciences” that was funded searches the lesion candidates in CT images by a pattern by Grant-in-Aid for Scientific Research on Innovative Areas, matching process. In the case of multi-disease detection from MEXT, Japan. The main purpose of our research in this project focus on model construction of computational anatomy and multi-organ, generating and matching a lot of prior lesion model applications for analyzing and recognizing the anatomical patterns from CT images can be tedious and sometimes not structures of human torso region using high-resolution torso X- possible.
    [Show full text]
  • David Eugene Smith Collection
    Ms Coll\Smith,D.E.\Historical Smith, David Eugene, 1860-1944, collector. Historical papers, [ca. 1400-1899] 17.5 linear ft.(ca. 10,100 items in 31 boxes) Biography: Mathematician. Professor of mathematics at the State Normal School, Cortland, N.Y., 1884-1891; at Michigan State Normal College, 1891-1898; at New York State Normal School, Brockport, N.Y., 1898-1901; and at Teachers College, Columbia University, 1901-1944. He was the editor of the Bulletin of the American Mathematical Society, the American Mathematical Monthly, and Scripta Mathematica, a member of the International Commission on the Teaching of Mathematics, 1908-1944; and librarian of Teachers College, 1902-1920. He was the author of Rara Mathemativca (1907), The History of Mathematics (1924), and many other works on the history of mathematics as well as over forty mathematical textbooks and numerous journal articles. He also collected manuscript materials relating to the history of mathematics. Summary: Correspondence, manuscripts, and documents of mathematicians and other scientists, often dealing with politics and fields other than mathematics. Many of these concern the French Revolution. Organization: Cataloged. * Alembert letters are available on microfilm (MN#2000-1207). Lalande letters are available on microfilm (MN#3605-4). Guillaume Libri letters are available in photocopy form. William John Clarke Miller are available on microfilm (MN#95-7023 to 95-2027). Gaspard Monge letters are available on microfilm (MN#80-1582). Selected Isaac Newton letters are available on microfilm (MN#3617-5). Selected Quetelet letters are available on microfilm (MN#3623-7). Finding aids: Contents list, 19p. Donor: Gift of David Eugene Smith, 1931.
    [Show full text]
  • Using Deep Learning Convolutional Neural Network
    Yang et al. BioMed Eng OnLine (2018) 17:138 https://doi.org/10.1186/s12938-018-0587-0 BioMedical Engineering OnLine RESEARCH Open Access Multimodal MRI‑based classifcation of migraine: using deep learning convolutional neural network Hao Yang†, Junran Zhang*†, Qihong Liu and Yi Wang *Correspondence: [email protected] Abstract †Hao Yang and Junran Zhang Background: Recently, deep learning technologies have rapidly expanded into medi- contributed equally to this work cal image analysis, including both disease detection and classifcation. As far as we Department of Medical know, migraine is a disabling and common neurological disorder, typically character- Information Engineering, ized by unilateral, throbbing and pulsating headaches. Unfortunately, a large number School of Electrical Engineering and Information, of migraineurs do not receive the accurate diagnosis when using traditional diagnostic Sichuan University, Chengdu, criteria based on the guidelines of the International Headache Society. As such, there Sichuan, China is substantial interest in developing automated methods to assist in the diagnosis of migraine. Methods: To the best of our knowledge, no studies have evaluated the potential of deep learning technologies in assisting with the classifcation of migraine patients. Here, we used deep learning methods in combination with three functional measures (the amplitude of low-frequency fuctuations, regional homogeneity and regional functional correlation strength) based on rs-fMRI data to distinguish not only between migraineurs and healthy controls, but also between the two subtypes of migraine. We employed 21 migraine patients without aura, 15 migraineurs with aura, and 28 healthy controls. Results: Compared with the traditional support vector machine classifer, which has an accuracy of 83.67%, our Inception module-based convolutional neural network approach showed a signifcant improvement in classifcation output (over 86.18%).
    [Show full text]
  • A Review on Deep Learning in Medical Image Reconstruction ∗
    A Review on Deep Learning in Medical Image Reconstruction ∗ Haimiao Zhang† and Bin Dong†‡ June 26, 2019 Abstract. Medical imaging is crucial in modern clinics to provide guidance to the diagnosis and treatment of diseases. Medical image reconstruction is one of the most fundamental and important components of medical imaging, whose major objective is to acquire high-quality medical images for clinical usage at the minimal cost and risk to the patients. Mathematical models in medical image reconstruction or, more generally, image restoration in computer vision, have been playing a promi- nent role. Earlier mathematical models are mostly designed by human knowledge or hypothesis on the image to be reconstructed, and we shall call these models handcrafted models. Later, handcrafted plus data-driven modeling started to emerge which still mostly relies on human designs, while part of the model is learned from the observed data. More recently, as more data and computation resources are made available, deep learning based models (or deep models) pushed the data-driven modeling to the extreme where the models are mostly based on learning with minimal human designs. Both handcrafted and data-driven modeling have their own advantages and disadvantages. Typical hand- crafted models are well interpretable with solid theoretical supports on the robustness, recoverability, complexity, etc., whereas they may not be flexible and sophisticated enough to fully leverage large data sets. Data-driven models, especially deep models, on the other hand, are generally much more flexible and effective in extracting useful information from large data sets, while they are currently still in lack of theoretical foundations.
    [Show full text]
  • Deep Learning in Bioinformatics
    Deep Learning in Bioinformatics Seonwoo Min1, Byunghan Lee1, and Sungroh Yoon1,2* 1Department of Electrical and Computer Engineering, Seoul National University, Seoul 08826, Korea 2Interdisciplinary Program in Bioinformatics, Seoul National University, Seoul 08826, Korea Abstract In the era of big data, transformation of biomedical big data into valuable knowledge has been one of the most important challenges in bioinformatics. Deep learning has advanced rapidly since the early 2000s and now demonstrates state-of-the-art performance in various fields. Accordingly, application of deep learning in bioinformatics to gain insight from data has been emphasized in both academia and industry. Here, we review deep learning in bioinformatics, presenting examples of current research. To provide a useful and comprehensive perspective, we categorize research both by the bioinformatics domain (i.e., omics, biomedical imaging, biomedical signal processing) and deep learning architecture (i.e., deep neural networks, convolutional neural networks, recurrent neural networks, emergent architectures) and present brief descriptions of each study. Additionally, we discuss theoretical and practical issues of deep learning in bioinformatics and suggest future research directions. We believe that this review will provide valuable insights and serve as a starting point for researchers to apply deep learning approaches in their bioinformatics studies. *Corresponding author. Mailing address: 301-908, Department of Electrical and Computer Engineering, Seoul National University, Seoul 08826, Korea. E-mail: [email protected]. Phone: +82-2-880-1401. Keywords Deep learning, neural network, machine learning, bioinformatics, omics, biomedical imaging, biomedical signal processing Key Points As a great deal of biomedical data have been accumulated, various machine algorithms are now being widely applied in bioinformatics to extract knowledge from big data.
    [Show full text]
  • Medical Image Computing: Machine-Learning Methods and Advanced-MRI Applications
    Medical Image Computing: Machine-learning methods and Advanced-MRI applications Overview Medical imaging is increasingly being used as a first step for clinical diagnosis of a large number of diseases, including disorders of the brain, heart, lung, kidney, muscle, etc. Among the modalities that find widespread use is magnetic resonance imaging (MRI), due its ability to image bones as well as soft tissue. In the case of major abnormalities such as tumors, a radiologist can easily spot abnormalities in the MR images. However, subtle changes in the tissue are difficult to locate for the human eye. Hence, advanced image processing techniques can be of great medical value to assist the radiologist as well as to understand the basic mechanism of action in a large number of diseases. Further, early diagnosis is critical for better clinical outcome. This course is designed as an introductory course in medical image processing and analysis for engineers and quantitative scientists, including students and faculty. It will primarily focus on MR imaging and analysis with a special emphasis on brain and mental disorders. Apart from the basics such as edge detection and segmentation, we will also cover advanced concepts such as shape analysis, probabilistic clustering, nonlinear dimensionality reduction, and diffusion MRI processing. This course will also have several hands-on segments that will allow the students to get a first-hand feel of the opportunities and challenges in medical image analysis. Course participants will learn these topics through lectures and hands-on experiments. Also, case studies and assignments will be shared to stimulate research motivation of participants.
    [Show full text]
  • MR Images, Brain Lesions, and Deep Learning
    applied sciences Review MR Images, Brain Lesions, and Deep Learning Darwin Castillo 1,2,3,* , Vasudevan Lakshminarayanan 2,4 and María José Rodríguez-Álvarez 3 1 Departamento de Química y Ciencias Exactas, Sección Fisicoquímica y Matemáticas, Universidad Técnica Particular de Loja, San Cayetano Alto s/n, Loja 11-01-608, Ecuador 2 Theoretical and Experimental Epistemology Lab, School of Optometry and Vision Science, University of Waterloo, Waterloo, ON N2L3G1, Canada; [email protected] 3 Instituto de Instrumentación para Imagen Molecular (i3M) Universitat Politècnica de València—Consejo Superior de Investigaciones Científicas (CSIC), E-46022 Valencia, Spain; [email protected] 4 Departments of Physics, Electrical and Computer Engineering and Systems Design Engineering, University of Waterloo, Waterloo, ON N2L3G1, Canada * Correspondence: [email protected]; Tel.: +593-07-370-1444 (ext. 3204) Featured Application: This review provides a critical review of deep/machine learning algo- rithms used in the identification of ischemic stroke and demyelinating brain diseases. It eval- uates their strengths and weaknesses when applied to real world clinical data. Abstract: Medical brain image analysis is a necessary step in computer-assisted/computer-aided diagnosis (CAD) systems. Advancements in both hardware and software in the past few years have led to improved segmentation and classification of various diseases. In the present work, we review the published literature on systems and algorithms that allow for classification, identification, and detection of white matter hyperintensities (WMHs) of brain magnetic resonance (MR) images, specifically in cases of ischemic stroke and demyelinating diseases. For the selection criteria, we used bibliometric networks. Of a total of 140 documents, we selected 38 articles that deal with the main objectives of this study.
    [Show full text]
  • Medical Image Processing: from Formation to Interpretation
    Technical Article Share on Twitter Facebook LinkedIn Email Medical Image Processing: From Formation to Interpretation Anton Patyuchenko Analog Devices, Inc. Technological advancements achieved in medical imaging over the last Core Areas of Medical Image Processing century created unprecedented opportunities for noninvasive diagnostic There are numerous concepts and approaches for structuring the field of and established medical imaging as an integral part of healthcare systems medical image processing that focus on different aspects of its core areas today. One of the major areas of innovation representing these advance- illustrated in Figure 1. These areas shape three major processes underlying ments is the interdisciplinary field of medical image processing. this field—image formation, image computing, and image management. This field of rapid development deals with a broad number of processes The process of image formation is comprised of data acquisition and ranging from raw data acquisition to digital image communication that image reconstruction steps, providing a solution to a mathematical inverse underpin the complete data flow in modern medical imaging systems. problem. The purpose of image computing is to improve interpretability of Nowadays, these systems offer increasingly higher resolutions in spatial the reconstructed image and extract clinically relevant informa tion from it. and intensity dimensions, as well as faster acquisition times resulting in an Finally, image management deals with compression, archiving, retrieval, extensive amount of high quality raw image data that must be properly and communication of the acquired images and derived information. processed and interpreted to attain accurate diagnostic results. This article focuses on the key areas of medical image processing, consid- ers the context of specific imaging modalities, and discusses the key challenges and trends in this field.
    [Show full text]
  • Computational Anatomy for Multi-Organ Analysis in Medical Imaging: a Review
    Medical Image Analysis 56 (2019) 44–67 Contents lists available at ScienceDirect Medical Image Analysis journal homepage: www.elsevier.com/locate/media Computational anatomy for multi-organ analysis in medical imaging: A review ∗ Juan J. Cerrolaza a, , Mirella López Picazo b,c, Ludovic Humbert c, Yoshinobu Sato d, Daniel Rueckert a, Miguel Ángel González Ballester b,e, Marius George Linguraru f,g a Biomedical Image Analysis Group, Imperial College London, United Kingdom b BCN Medtech, Dept. of Information and Communication Technologies, Universitat Pompeu Fabra, Barcelona, Spain c Galgo Medical S.L., Spain d Graduate School of Information Science, Nara Institute of Science and Technology (NAIST), Nara, Japan e ICREA, Barcelona, Spain f Sheickh Zayed Institute for Pediatric Surgicaonl Innovation, Children’s National Health System, Washington DC, USA g School of Medicine and Health Sciences, George Washington University, Washington DC, USA a r t i c l e i n f o a b s t r a c t Article history: The medical image analysis field has traditionally been focused on the development of organ-, and Received 20 August 2018 disease-specific methods. Recently, the interest in the development of more comprehensive computa- Revised 5 February 2019 tional anatomical models has grown, leading to the creation of multi-organ models. Multi-organ ap- Accepted 13 April 2019 proaches, unlike traditional organ-specific strategies, incorporate inter-organ relations into the model, Available online 15 May 2019 thus leading to a more accurate representation of the complex human anatomy. Inter-organ relations Keywords: are not only spatial, but also functional and physiological.
    [Show full text]
  • Introduction to Medical Image Computing
    1 MEDICAL IMAGE COMPUTING (CAP 5937)- SPRING 2017 LECTURE 1: Introduction Dr. Ulas Bagci HEC 221, Center for Research in Computer Vision (CRCV), University of Central Florida (UCF), Orlando, FL 32814. [email protected] or [email protected] 2 • This is a special topics course, offered for the second time in UCF. Lorem Ipsum Dolor Sit Amet CAP5937: Medical Image Computing 3 • This is a special topics course, offered for the second time in UCF. • Lectures: Mon/Wed, 10.30am- 11.45am Lorem Ipsum Dolor Sit Amet CAP5937: Medical Image Computing 4 • This is a special topics course, offered for the second time in UCF. • Lectures: Mon/Wed, 10.30am- 11.45am • Office hours: Lorem Ipsum Dolor Sit Amet Mon/Wed, 1pm- 2.30pm CAP5937: Medical Image Computing 5 • This is a special topics course, offered for the second time in UCF. • Lectures: Mon/Wed, 10.30am-11.45am • Office hours: Mon/Wed, 1pm- 2.30pm • No textbook is Lorem Ipsum Dolor Sit Amet required, materials will be provided. • Avg. grade was A- last CAP5937: Medical Image Computing spring. 6 Image Processing Computer Vision Medical Image Imaging Computing Sciences (Radiology, Biomedical) Machine Learning 7 Motivation • Imaging sciences is experiencing a tremendous growth in the U.S. The NYT recently ranked biomedical jobs as the number one fastest growing career field in the nation and listed bio-medical imaging as the primary reason for the growth. 8 Motivation • Imaging sciences is experiencing a tremendous growth in the U.S. The NYT recently ranked biomedical jobs as the number one fastest growing career field in the nation and listed bio-medical imaging as the primary reason for the growth.
    [Show full text]
  • Lars Ruthotto
    Lars Ruthotto 400 Dowman Dr, W408 [email protected] 30322 Atlanta, GA http://www.mathcs.emory.edu/~lruthot/ United States @lruthotto Education Doctor of Natural Sciences, University of M¨unster,Germany, 2012, thesis entitled Hyperelastic Image Registration - Theory, Numerical Methods, and Applications, advisors: Martin Burger and Jan Modersitzki. Diploma in Mathematics, University of M¨unster,Germany, 2010. Full-time Positions Associate Professor, Departments of Mathematics and Computer Science, Emory University, since Sept. 2020. Assistant Professor, Departments of Mathematics and Computer Science, Emory University, Sept. 2014 { Aug. 2020. Postdoctoral Research Fellow, Department of Mathematics / Earth and Ocean Sciences, University of British Columbia, Canada, Jan. 2013 { Aug. 2014. Research and Teaching Assistant, Institute of Mathematics and Image Computing, University of L¨ubeck, Germany, Oct. 2010 { Dec. 2012. Research Assistant, Institute of Biomagnetism and Biosignalanalysis, University of M¨unster,Germany, Aug. and Sept. 2010. Research and Teaching Assistant, Institute for Computational and Applied Mathematics, University of M¨unster,Germany, April 2010 { July 2010. Other Positions Senior Fellow, Institute for Pure and Applied Mathematics (IPAM), Long program on Machine Learning for Physics and the Physics of Learning Tutorials, Sept. 2019 { Dec. 2019. Senior Consultant, XTract Technologies Inc., Jan. 2017 { Sept. 2019. Publications Submitted Papers and Preprints [P.6] Onken D, Nurbekyan L, Li X, Wu Fung S, Osher S, Ruthotto
    [Show full text]